The base adapter's auto-TTS path fired on any voice message unless the chat had explicitly run /voice off — it never read voice.auto_tts from config.yaml, so users who set auto_tts: false still got audio replies. Gate the base adapter on a three-layer decision instead: 1. chat in _auto_tts_enabled_chats (explicit /voice on|tts) → fire 2. chat in _auto_tts_disabled_chats (explicit /voice off) → suppress 3. else → voice.auto_tts global default Runner now pushes voice.auto_tts onto the adapter as _auto_tts_default and mirrors /voice on|tts chats into _auto_tts_enabled_chats via the existing _sync_voice_mode_state_to_adapter path. /voice off still wins. Closes #16007.
This commit is contained in:
Teknium
@@ -1025,7 +1025,20 @@ class BasePlatformAdapter(ABC):
|
||||
self._post_delivery_callbacks: Dict[str, Any] = {}
|
||||
self._expected_cancelled_tasks: set[asyncio.Task] = set()
|
||||
self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
|
||||
# Chats where auto-TTS on voice input is disabled (set by /voice off)
|
||||
# Auto-TTS on voice input: ``_auto_tts_default`` is the global default
|
||||
# (``voice.auto_tts`` in config.yaml, pushed by GatewayRunner on connect).
|
||||
# Per-chat overrides live in two sets populated from ``_voice_mode``:
|
||||
# - ``_auto_tts_enabled_chats``: chat explicitly opted in via ``/voice on``
|
||||
# or ``/voice tts`` (mode is ``voice_only`` or ``all``). Fires even when
|
||||
# the global default is False.
|
||||
# - ``_auto_tts_disabled_chats``: chat explicitly opted out via
|
||||
# ``/voice off`` (mode is ``off``). Suppresses auto-TTS even when the
|
||||
# global default is True.
|
||||
# The gate in _process_message() is:
|
||||
# fire if chat in _auto_tts_enabled_chats
|
||||
# OR (_auto_tts_default and chat not in _auto_tts_disabled_chats)
|
||||
self._auto_tts_default: bool = False
|
||||
self._auto_tts_enabled_chats: set = set()
|
||||
self._auto_tts_disabled_chats: set = set()
|
||||
# Chats where typing indicator is paused (e.g. during approval waits).
|
||||
# _keep_typing skips send_typing when the chat_id is in this set.
|
||||
@@ -1047,6 +1060,21 @@ class BasePlatformAdapter(ABC):
|
||||
def fatal_error_retryable(self) -> bool:
|
||||
return self._fatal_error_retryable
|
||||
|
||||
def _should_auto_tts_for_chat(self, chat_id: str) -> bool:
|
||||
"""Whether auto-TTS on voice input should fire for ``chat_id``.
|
||||
|
||||
Decision layers (Issue #16007):
|
||||
1. Explicit ``/voice on`` or ``/voice tts`` → always fire (even if
|
||||
``voice.auto_tts`` is False).
|
||||
2. Explicit ``/voice off`` → never fire.
|
||||
3. Fall back to the global ``voice.auto_tts`` config default.
|
||||
"""
|
||||
if chat_id in self._auto_tts_enabled_chats:
|
||||
return True
|
||||
if chat_id in self._auto_tts_disabled_chats:
|
||||
return False
|
||||
return bool(self._auto_tts_default)
|
||||
|
||||
def set_fatal_error_handler(self, handler: Callable[["BasePlatformAdapter"], Awaitable[None] | None]) -> None:
|
||||
self._fatal_error_handler = handler
|
||||
|
||||
@@ -2214,12 +2242,14 @@ class BasePlatformAdapter(ABC):
|
||||
logger.info("[%s] extract_local_files found %d file(s) in response", self.name, len(local_files))
|
||||
|
||||
# Auto-TTS: if voice message, generate audio FIRST (before sending text)
|
||||
# Skipped when the chat has voice mode disabled (/voice off)
|
||||
# Gated via ``_should_auto_tts_for_chat``: fires when the chat has
|
||||
# an explicit ``/voice on|tts`` opt-in OR when ``voice.auto_tts`` is
|
||||
# True globally and no ``/voice off`` has been issued.
|
||||
_tts_path = None
|
||||
if (event.message_type == MessageType.VOICE
|
||||
if (self._should_auto_tts_for_chat(event.source.chat_id)
|
||||
and event.message_type == MessageType.VOICE
|
||||
and text_content
|
||||
and not media_files
|
||||
and event.source.chat_id not in self._auto_tts_disabled_chats):
|
||||
and not media_files):
|
||||
try:
|
||||
from tools.tts_tool import text_to_speech_tool, check_tts_requirements
|
||||
if check_tts_requirements():
|
||||
|
||||
@@ -881,23 +881,74 @@ class GatewayRunner:
|
||||
return
|
||||
if disabled:
|
||||
disabled_chats.add(chat_id)
|
||||
# ``/voice off`` also clears any explicit enable — it's a hard override.
|
||||
enabled_chats = getattr(adapter, "_auto_tts_enabled_chats", None)
|
||||
if isinstance(enabled_chats, set):
|
||||
enabled_chats.discard(chat_id)
|
||||
else:
|
||||
disabled_chats.discard(chat_id)
|
||||
|
||||
def _sync_voice_mode_state_to_adapter(self, adapter) -> None:
|
||||
"""Restore persisted /voice off state into a live platform adapter."""
|
||||
disabled_chats = getattr(adapter, "_auto_tts_disabled_chats", None)
|
||||
if not isinstance(disabled_chats, set):
|
||||
def _set_adapter_auto_tts_enabled(self, adapter, chat_id: str, enabled: bool) -> None:
|
||||
"""Update an adapter's per-chat auto-TTS opt-in set if present.
|
||||
|
||||
Used for ``/voice on``/``/voice tts`` where the user explicitly wants
|
||||
auto-TTS even when ``voice.auto_tts`` is False globally.
|
||||
"""
|
||||
enabled_chats = getattr(adapter, "_auto_tts_enabled_chats", None)
|
||||
if not isinstance(enabled_chats, set):
|
||||
return
|
||||
if enabled:
|
||||
enabled_chats.add(chat_id)
|
||||
# An explicit opt-in clears any stale /voice off for this chat.
|
||||
disabled_chats = getattr(adapter, "_auto_tts_disabled_chats", None)
|
||||
if isinstance(disabled_chats, set):
|
||||
disabled_chats.discard(chat_id)
|
||||
else:
|
||||
enabled_chats.discard(chat_id)
|
||||
|
||||
def _sync_voice_mode_state_to_adapter(self, adapter) -> None:
|
||||
"""Restore persisted /voice state into a live platform adapter.
|
||||
|
||||
Populates three fields from config + ``self._voice_mode``:
|
||||
- ``_auto_tts_default``: global default from ``voice.auto_tts``
|
||||
- ``_auto_tts_enabled_chats``: chats with mode ``voice_only``/``all``
|
||||
- ``_auto_tts_disabled_chats``: chats with mode ``off``
|
||||
"""
|
||||
platform = getattr(adapter, "platform", None)
|
||||
if not isinstance(platform, Platform):
|
||||
return
|
||||
disabled_chats.clear()
|
||||
|
||||
disabled_chats = getattr(adapter, "_auto_tts_disabled_chats", None)
|
||||
enabled_chats = getattr(adapter, "_auto_tts_enabled_chats", None)
|
||||
if not isinstance(disabled_chats, set) and not isinstance(enabled_chats, set):
|
||||
return
|
||||
|
||||
# Push the global voice.auto_tts default (config.yaml) onto the adapter.
|
||||
# Lazy import to avoid adding a module-level dep from gateway → hermes_cli.
|
||||
try:
|
||||
from hermes_cli.config import load_config as _load_full_config
|
||||
_full_cfg = _load_full_config()
|
||||
_auto_tts_default = bool(
|
||||
(_full_cfg.get("voice") or {}).get("auto_tts", False)
|
||||
)
|
||||
except Exception:
|
||||
_auto_tts_default = False
|
||||
if hasattr(adapter, "_auto_tts_default"):
|
||||
adapter._auto_tts_default = _auto_tts_default
|
||||
|
||||
prefix = f"{platform.value}:"
|
||||
disabled_chats.update(
|
||||
key[len(prefix):] for key, mode in self._voice_mode.items()
|
||||
if mode == "off" and key.startswith(prefix)
|
||||
)
|
||||
if isinstance(disabled_chats, set):
|
||||
disabled_chats.clear()
|
||||
disabled_chats.update(
|
||||
key[len(prefix):] for key, mode in self._voice_mode.items()
|
||||
if mode == "off" and key.startswith(prefix)
|
||||
)
|
||||
if isinstance(enabled_chats, set):
|
||||
enabled_chats.clear()
|
||||
enabled_chats.update(
|
||||
key[len(prefix):] for key, mode in self._voice_mode.items()
|
||||
if mode in ("voice_only", "all") and key.startswith(prefix)
|
||||
)
|
||||
|
||||
async def _safe_adapter_disconnect(self, adapter, platform) -> None:
|
||||
"""Call adapter.disconnect() defensively, swallowing any error.
|
||||
@@ -5977,7 +6028,7 @@ class GatewayRunner:
|
||||
self._voice_mode[voice_key] = "voice_only"
|
||||
self._save_voice_modes()
|
||||
if adapter:
|
||||
self._set_adapter_auto_tts_disabled(adapter, chat_id, disabled=False)
|
||||
self._set_adapter_auto_tts_enabled(adapter, chat_id, enabled=True)
|
||||
return (
|
||||
"Voice mode enabled.\n"
|
||||
"I'll reply with voice when you send voice messages.\n"
|
||||
@@ -5993,7 +6044,7 @@ class GatewayRunner:
|
||||
self._voice_mode[voice_key] = "all"
|
||||
self._save_voice_modes()
|
||||
if adapter:
|
||||
self._set_adapter_auto_tts_disabled(adapter, chat_id, disabled=False)
|
||||
self._set_adapter_auto_tts_enabled(adapter, chat_id, enabled=True)
|
||||
return (
|
||||
"Auto-TTS enabled.\n"
|
||||
"All replies will include a voice message."
|
||||
@@ -6032,7 +6083,7 @@ class GatewayRunner:
|
||||
self._voice_mode[voice_key] = "voice_only"
|
||||
self._save_voice_modes()
|
||||
if adapter:
|
||||
self._set_adapter_auto_tts_disabled(adapter, chat_id, disabled=False)
|
||||
self._set_adapter_auto_tts_enabled(adapter, chat_id, enabled=True)
|
||||
return "Voice mode enabled."
|
||||
else:
|
||||
self._voice_mode[voice_key] = "off"
|
||||
@@ -6083,7 +6134,7 @@ class GatewayRunner:
|
||||
adapter._voice_sources[guild_id] = event.source.to_dict()
|
||||
self._voice_mode[self._voice_key(event.source.platform, event.source.chat_id)] = "all"
|
||||
self._save_voice_modes()
|
||||
self._set_adapter_auto_tts_disabled(adapter, event.source.chat_id, disabled=False)
|
||||
self._set_adapter_auto_tts_enabled(adapter, event.source.chat_id, enabled=True)
|
||||
return (
|
||||
f"Joined voice channel **{voice_channel.name}**.\n"
|
||||
f"I'll speak my replies and listen to you. Use /voice leave to disconnect."
|
||||
|
||||
Reference in New Issue
Block a user